Tidy Tuesday 05-31-2022: Company Reputation Poll

poll <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-05-31/poll.csv')

## Rows: 500 Columns: 8
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): company, industry
## dbl (6): 2022_rank, 2022_rq, change, year, rank, rq
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

reputation <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-05-31/reputation.csv')

## Rows: 700 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): company, industry, name
## dbl (2): score, rank
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

top_2022 <- poll %>%
   rename(rank_2022 = `2022_rank`) %>%
  filter(rank_2022 < 21)

industry_2021 <- poll %>%
  rename(rank_2022 = `2022_rank`) %>%
  drop_na(rank) %>%
  filter(year == 2021) %>%
  group_by(industry) %>%
  count()

industry_2021 <- industry_2021 %>%
  mutate(proportion = n/100)

industry_2020 <- poll %>%
  rename(rank_2022 = `2022_rank`) %>%
  drop_na(rank) %>%
  filter(year == 2020) %>%
  group_by(industry) %>%
  count() %>%
  mutate(proportion = n/100)

industry_2019 <- poll %>%
  rename(rank_2022 = `2022_rank`) %>%
  drop_na(rank) %>%
  filter(year == 2019) %>%
  group_by(industry) %>%
  count() %>%
  mutate(proportion = n/100)

industry_2018 <- poll %>%
  rename(rank_2022 = `2022_rank`) %>%
  drop_na(rank) %>%
  filter(year == 2018) %>%
  group_by(industry) %>%
  count() %>%
  mutate(proportion = n/100)

industry_2017 <- poll %>%
  rename(rank_2022 = `2022_rank`) %>%
  drop_na(rank) %>%
  filter(year == 2017) %>%
  group_by(industry) %>%
  count() %>%
  mutate(proportion = n/100)

  y.breaks.2017 <- cumsum(industry_2017$proportion) - industry_2017$proportion/2

fig <- plot_ly() 

fig <- fig %>% add_pie(data = industry_2017, labels = ~industry, values = ~proportion,
                         name = "2017", domain = list(row = 0, column = 0))
fig <- fig %>% add_pie(data = industry_2018, labels = ~industry, values = ~proportion,
                         name = "2018", domain = list(row = 0, column = 1))
fig <- fig %>% add_pie(data = industry_2019, labels = ~industry, values = ~proportion,
                         name = "2019", domain = list(row = 1, column = 0))
fig <- fig %>% add_pie(data = industry_2020, labels = ~industry, values = ~proportion,
                         name = "2020", domain = list(row = 1, column = 1))
fig <- fig %>% add_pie(data = industry_2021, labels = ~industry, values = ~proportion,
                         name = "2021", domain = list(row = 2, column = 2))

fig <- fig %>% layout(title = "Proportion of Top 100 Rankings per Industry by Year", showlegend = F,
                      grid=list(rows=3, columns=2),
                      xaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE),
                      yaxis = list(showgrid = FALSE, zeroline = FALSE, showticklabels = FALSE))
fig